https://irjet.net/archives/V4/i3/IRJET-V4I3156.pdf

1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 3 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 566
Service Rating Prediction by check-in and check-out behavior of user
and POI
Bhushan Patil, Siddheshwar Anajekar, Ganesh More, Sujit Dhaware
Students , B.E Computer , JSPM Narhe Technical Campus ,Pune , India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Now’s days over 200 million customers
online to the world-wide web, and E-commerce of
world trade. Throw the uses of mobile device and
techniques have fundamentally enhanced social
networks services, such as Facebook, twitter, Google
plus, LinkedIn, etc. which allows users to share their
experiences, reviews, ratings, photos, check-ins, video,
audio ,etc. The user geographical information located
by smart phone bridges the gap between physical and
digital worlds. The new factors of social network like
interpersonal exchange and interest based on circles of
friends and challenges for recommender system (RS).
Location data functions as the connection between
user’s physical behaviors and social networks service
by the smart phone or web services. We refer to these
social networks know to geographical information as
location-based social networks (LBSN).We
mine:(1)user’s rating for any item.(2) between user’s
rating differences and user-user.(3)interpersonal
interest similarity, are a unified rating prediction
modules are used to communicate with the user.
Key Words: Big data, Geographical location, Social
network services, Recommender systems, Rating
prediction, Smart Phones, Predictive models, User rating
confidence, Mobile communication, Personal interest ,E-
commerce ,Web mining.
INTRODUCTION :
Now a days rapid development of ubiquitous internet
access and use of different mobile devices , social media
such as facebook , twitter , linkedin are widespread . smart
phone users produce large volumes of data . The internet
revolution has brought about a new way of expressing an
individual's opinion. It has become a medium through
which people openly express their views on various
subjects. These opinions contain useful information which
can be utilized in many sectors which require constant
customer feedback. The proposed method attempts to
overcome the problem of the loss of text information by
using well trained training sets. Also, recommendation of a
product or request for a product as per the user’s
requirements have achieved with the proposed method.
Big data has received considerable attention, because it
can mine new knowledge for economic growth and
technical innovation .The data in this competition is a
random selection from Hotels and is not representative of
the overall statistics. System is being designed such a way
that in predicting which hotel group a user is going to
book. Where similar hotels for a search (based on
historical price, customer star ratings, geographical
locations relative to city center, etc.) are grouped together.
When users take a long journey, they may keep a good
emotion and try their best Service to have a very nice trip.
Most of the services they consume are the local featured
things. They can give high ratings more easily than the
local rating. This can helpful us to constrain rating
prediction.
In addition information, when users take a long distance
travelling for an away new city as strangers. They may
depend more on their local friends. Therefore, users’ and
their local friends’ ratings may be similar. It helps us to
constrain rating prediction. Furthermore, if the
geographical location factor is ignored, when we search
the Internet for a travel, recommender systems may
recommend us a new scenic spot without considering
whether there are local friends to help us to plan the trip
or not. But if recommender systems consider geographical
location actor, the recommendations may be more
humanized and thoughtful. These are the motivations why
we utilize geographical location information to make
rating prediction.
With the above motivations, the goals of this paper are: 1)
to mine the relevance between user’s ratings and user
item geographical location distances, called as user-item
geographical connection, 2) to mine the relevance
between users’ rating differences and user-user
geographical location distances, called as user-user
geographical connection, and 3) to find the people whose
interest is similar to users. In this paper, three factors are
taken into consideration for rating prediction: user-item
geographical connection, user-user geographical
connection, and interpersonal interest similarity. These
factors are fused into a location based rating prediction
model. The novelties of this paper are user-item and user-
user geographical connections, i.e. we explore users’ rating
behaviors through their geographical location distances.
The main contributions of this paper are summarized as
follows:

2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 3 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 567
 We mine the relevance between ratings and user
item geographical location distances. It is
discovered that users usually give high scores to
the items (or services) which are very far away
from their activity centers. It can help us to
understand users’ rating behaviors for
recommendation
 We mine the relevance between users’ rating
differences and user-user geographical distances.
It is discovered that users and their
geographically far away friends usually give the
similar scores to the same item. It can help us to
understand users’ rating behaviors for
recommendation.
 We integrate three factors: user-item
geographical connection, user-user geographical
connection, and interpersonal interest similarity,
into a Location Based Rating Prediction (LBRP)
model. The proposed model is evaluated by
extensive experiments based on Yelp dataset.
Experimental results show significant
improvement compared with existing approaches.
Literature survey : The focus of the literature survey is
to study and collect the information of user behavior from
reviews or opinion based on semantics for service system
and features of domain of service system.
1. Shunmei Meng et al. focused on keyword based service
recommender system which analyzes present and past
user’s behavior searching best hotel list as per their
requirement through reviews posted by users. It actually
dose preprocessing of HTML for collecting set of keywords
like food, accommodation, location etc. to form candidate
set which is fed to approximate and exact similarity
computation algorithm along with preferences of current
and past user reviews.
2. Lisette García-Moya et al. focused on identification of
aspects or feature of product from customer’s reviews
about product features, semantic classification from
opinion of customer and aspect ranking is identifying
relevance of aspect and opinion. This system considers
stochastic mappings between words to estimate a unigram
language model of product features. It determines the
probabilistic model for mapping opinion to product
feature by retrieving words from reviews based on co-
occurrence vale and refining them. Finally evaluation of
retrieval is done using HITS method.
These existing methods of extraction of prediction from
user are useful for only limited database, but if there are
hug datasets then it is difficult to analyze prediction of
users review there for this system is proposed which is
using Hadoop for Big data analysis, and Map reduce for
further processing of data.
Existing system:
 The system consists of application software on
smart phone , web server , database server
 The Hadoop distributed file system is used to
handle the database
 For location purpose the GPS is used
Proposed System :
 Main perspective of this system is to provide
recommendation of a particular hotel on the
basis of users review. System uses Geographical
location of user, if he is login to the system from
particular location, suppose Pune then he is able
to see first that location’s recommended hotels.
 Also system uses NLP technique to suggest best
Hotel in that area. If there are number of hotels
having recommendation then difficult to choose,
using NLP it is easy to decide because it sorts
hotel according to Positive and negative
recommendations, so hotel having positive
comments that will see first
 Architecture:
Hardware Requirements:
 4 GB of RAM
 And multiple systems are user wants to have a
cluster node setup.
 Database proposed: HDFS

3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 3 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 568
Software Requirements:
 Operating system: LINUX centos 6.7
 Language: JAVA, HADOOP.
Conclusion: We compare the performances of the three
independent Factors was proposed by combining social
network factors: personal interest similarity,
interpersonal interest similarity, and interpersonal items
and these factors were fused together to improve real-
time items accuracy and applicability of recommender
system. We conducted extensive experiments on three
large real-world social rating datasets, and showed
significant improvements over existing approaches that
use mixed social network information. In our future
works, we will take user location information to
recommend more personalized and real-time items.
References:
[1] J. Zhang and C. Chow, “Spatiotemporal Sequential
Influence Modeling for Location
Recommendations: A Gravity-based Approach,”
ACM Transactions on the Intelligent Systems and
Technology, Accepted.
[2] J. Zhang, C. Chow, and Y. Li, “LORE: Exploiting
Sequential Influence for Location
Recommendations,”2014.
[3] R. Sinnott, “Virtues of the haversine”, Sky &
Telescope, vol. 68,no. 2, pp. 159.
[4] S. Jiang, X. Qian, Y. Fu, and T. Mei, “Author Topic
Model-based Collaborative Filtering for
Personalized POI Recommendations, ”IEEE Trans.
Multimedia, vol. 17, no. 6.
[5] G. Zhao, X. Qian, “Service Objective Evaluation via
Exploring Social Users’ Rating Behaviors”.
[6] G. Zhao, X. Qian, “Prospects and Challenges of
Deep Understanding Social Users and Urban
Services – a position paper,” in Proc. BigMM,
2015, pp. 15-20.
[7] M. Richardson and P. Domingos, “Mining
knowledge-sharing sites for viral market1ing,” in
Proc. KDD,pp. 61–70.
[8] X.-W.Yang, H. Steck, andY. Liu, “Circle-based
recommendation in online social networks,” in
Proc. KDD, 2013, pp. 1267–1276.
[9] M. Jiang et al., “Social contextual
recommendation,” in Proc. CIKM,2013, pp. 45–56.
[10] M. Jamali and M. Ester, “A matrix factorization
technique with trust propagation for
recommendation in social networks,” in Proc.
2010, pp. 135–142.
[11] H. Ma, I. King, and M. R. Lyu, “Learning to
recommend with social trust ensemble,” in Proc.
SIGIR, 2009, pp. 203–210.
[12] M. Jamali andM. Ester, “Trustwalker: A random
walk model for combining trust-based and item-
based recommendation,” Proc. KDD, 2009.
[13] X. Yang, Y. Guo, and Y. Liu, “Bayesian-inference
recommendation in online social networks,” in
Proc. INFOCOM, 2011.
[14] J. Zhang, C. Chow, and Y. Li, “iGeoRec: A
Personalized and Efficient Geographical Location
Recommendation Framework, ”IEEE Transactions
on Services Computing.
[15] J. Zhang and C. Chow, “TICRec: A Probabilistic
Framework to Utilize Temporal Influence
orrelations for Time-aware Location
Recommendations,” IEEE Transactions Services
Computing,2015.
[16] J. Zhang , “CoRe: Exploiting the Personalized
Influence of Two-dimensional Geographic
coordinates for Location Recommendations,”
Information ciences,pp.163-181, 2015.
[17] J. Sang, T. Mei, “Activity sensor: Check-in usage
mining for local recommendation,” ACM
Transactions on Intelligent Systems and
Technology.
[18] J. Zhang and Chow, “GeoSoCa: Exploiting
Geographical, Social and Categorical Correlations
for Point-of-Interest Recommendations ,”ACM
SIGIR’15, 2015.
[19] Service Rating Prediction by Exploring Social
Mobile Users’ Geographical Locations .Guo shuai
Zhao, Xueming Qian, Member, IEEE, Chen Kang-
2016